Peter Lind

Peter Lind


I have a long background from database design, data analysis, programming and systems design, mostly from pharmaceutical industry where I worked with analysis of structure-activity relationships and development of the computing environment.

I have worked on MEB, KI with systems development for the CEDI eating disorder projects since January 2019.


I am the main author of the following papers:

  • Construction and Use of Fragment-Augmented Molecular Hasse Diagrams Jan 19, 2014, Journal of Chemical Information and Modeling
  • A Database-centric Virtual Chemistry System. Mar 16, 2006, Journal of Chemical Information and Computer Science, 2006
  • QSAR Analysis Involving Assay Results Which are only Known to be Greater Than, or Less Than Some Cut-off Limit.  Molecular Informatics, 2010.
  • Support Vector Machines for the Estimation of Aqueous Solubility Journal of Chemical Information and Computer Science. 2003.
    • This was the first paper demonstrating usefulness of support vector machine regression in a cheminformatics context. We noted that the Tanimoto function, which is often used to compare molecular fingerprints, fulfills the necessary conditions of a kernel function. This means that chemical fingerprints can be used for SVM regression.

Co-author of:

  • Phenethylthiazolethiourea (PETT) Compounds, a New Class of HIV-1 Reverse Transcriptase Inhibitors. 1. Synthesis and Basic Structure-Activity Relationship Studies of PETT Analogs Oct 11, 1996, J. Med. Chem. I designed and performed the first synthesis of HIV inhibitor Trovirdine.
    • This compound entered phase one clinical trials for potential use in the treatment of AIDS.

Also co-author of several other medicinal chemistry papers and patents.

In 2016-2017 I proposed and authored NIH SBIR grant applications for development of two fundamentally new machine learning and data analysis methods. Both grants were won. This was for US software company CDD, Inc.